AI Paper Atlas

Research map / Optimization / Optimizers

Momentum Centering and Asynchronous Update for Adaptive Gradient Methods

Juntang Zhuang, Yifan Ding, Tommy Ming Tang, Nicha C Dvornek, sekhar tatikonda, James s Duncan

NeurIPS 2021 · Optimization › Optimizers · approach: SGD momentum and step-size schedules · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use asynchronous centering instead of synchronous centeringAdaBelief-style adaptive optimization · ImageNetTop-1 accuracy: 70.08$\ddag$ -> \textbf{70.46}Improved
Use asynchronous centering instead of synchronous centeringTransformer · DE-ENBLEU: 35.17$\pm$0.015 -> \textbf{35.35$\pm$0.012}Improved
Use asynchronous centering instead of synchronous centeringTransformer · JA-ENBLEU: \textbf{34.38$\pm$0.009} -> 33.70$\pm$0.021Hurt
Use asynchronous centering instead of synchronous centeringGAN training · DCGANFID: 47.25$\pm$0.79 -> \textbf{43.43$\pm$4.38}Improved
Use asynchronous centering instead of synchronous centeringGAN training · RLGANFID: \textbf{36.58$\pm$0.12} -> 37.15$\pm$0.13Hurt
Use asynchronous centering instead of synchronous centeringGAN training · SNGANFID: 12.70$\pm$0.17 -> \textbf{12.44$\pm$0.02}Improved
Use asynchronous centering instead of synchronous centeringGAN training · SAGANFID: 13.98$\pm$0.02 -> \textbf{13.54$\pm$0.15}Improved
Use asynchronous updates rather than synchronous updatesAdaptive optimizers on the Reddi et al. periodic convex example · Online convex optimizationconvergenceImproved
Add centered second momentum to asynchronous updates (ablation)AdaShift · Sparse-gradient periodic convex problemconvergenceImproved
Use centered rather than uncentered second momentum (ablation)Asynchronous adaptive optimization · Stochastic non-convex optimizationupper bound on regretImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy